{"list":"other","total":70,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"id":"2211.15661","title":"What learning algorithm is in-context learning? Investigations with linear models","created":"2022-11-28","cited_by_count":684},{"id":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1707.02038","title":"A Tutorial on Thompson Sampling","created":"2017-07-07","cited_by_count":433},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370},{"id":"2012.15085","title":"Is Pessimism Provably Efficient for Offline RL?","created":"2020-12-30","cited_by_count":364},{"id":"2205.05055","title":"Data Distributional Properties Drive Emergent In-Context Learning in Transformers","created":"2022-04-22","cited_by_count":309},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304},{"id":"2103.12021","title":"Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism","created":"2021-03-22","cited_by_count":279},{"id":"1803.11347","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","created":"2018-03-30","cited_by_count":276},{"id":"1301.2609","title":"Learning to Optimize Via Posterior Sampling","created":"2013-01-11","cited_by_count":256},{"id":"1306.0940","title":"(More) Efficient Reinforcement Learning via Posterior Sampling","created":"2013-06-04","cited_by_count":233},{"id":"2006.10814","title":"FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs","created":"2020-06-18","cited_by_count":233},{"id":"1806.03335","title":"Randomized Prior Functions for Deep Reinforcement Learning","created":"2018-06-08","cited_by_count":219},{"id":"1910.08348","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","created":"2019-10-18","cited_by_count":217},{"id":"2002.08396","title":"Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning","created":"2020-02-19","cited_by_count":215},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214},{"id":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164},{"id":"2206.13499","title":"Prompting Decision Transformer for Few-Shot Policy Generalization","created":"2022-06-27","cited_by_count":146},{"id":"2202.07206","title":"Impact of Pretraining Term Frequencies on Few-Shot Reasoning","created":"2022-02-15","cited_by_count":142},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138},{"id":"1802.07245","title":"Meta-Reinforcement Learning of Structured Exploration Strategies","created":"2018-02-20","cited_by_count":130},{"id":"2207.04179","title":"Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling","created":"2022-07-09","cited_by_count":127},{"id":"2303.07895","title":"The Learnability of In-Context Learning","created":"2023-03-14","cited_by_count":127},{"id":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111},{"id":"2212.04458","title":"General-Purpose In-Context Learning by Meta-Learning Transformers","created":"2022-12-08","cited_by_count":105},{"id":"2008.06043","title":"Offline Meta-Reinforcement Learning with Advantage Weighting","created":"2020-08-13","cited_by_count":93},{"id":"1810.06784","title":"ProMP: Proximal Meta-Policy Search","created":"2018-10-16","cited_by_count":91},{"id":"2204.13509","title":"On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model","created":"2022-04-28","cited_by_count":81},{"id":"1905.06424","title":"Meta reinforcement learning as task inference","created":"2019-05-15","cited_by_count":77},{"id":"2205.13703","title":"Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters","created":"2022-05-27","cited_by_count":76},{"id":"2206.01079","title":"When does return-conditioned supervised learning work for offline reinforcement learning?","created":"2022-06-02","cited_by_count":76},{"id":"2204.04875","title":"Learning to Induce Causal Structure","created":"2022-04-11","cited_by_count":68},{"id":"1705.07347","title":"Ensemble Sampling","created":"2017-05-20","cited_by_count":62},{"id":"2008.02790","title":"Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices","created":"2020-08-06","cited_by_count":59},{"id":"2107.03974","title":"Offline Meta-Reinforcement Learning with Online Self-Supervision","created":"2021-07-08","cited_by_count":53},{"id":"2202.08417","title":"Retrieval-Augmented Reinforcement Learning","created":"2022-02-17","cited_by_count":53},{"id":"2210.13435","title":"Dichotomy of Control: Separating What You Can Control from What You Cannot","created":"2022-10-24","cited_by_count":47},{"id":"2107.01509","title":"Bayesian decision-making under misspecified priors with applications to meta-learning","created":"2021-07-03","cited_by_count":44},{"id":"2304.08487","title":"Hyper-Decision Transformer for Efficient Online Policy Adaptation","created":"2023-04-17","cited_by_count":33},{"id":"2302.09205","title":"Approximate Thompson Sampling via Epistemic Neural Networks","created":"2023-02-18","cited_by_count":31},{"id":"2104.02293","title":"On the Optimality of Batch Policy Optimization Algorithms","created":"2021-04-06","cited_by_count":28},{"id":"1509.06841","title":"One-Shot Learning of Manipulation Skills with Online Dynamics Adaptation and Neural Network Priors","created":"2015-09-23","cited_by_count":26},{"id":"2212.04590","title":"Learning Options via Compression","created":"2022-12-08","cited_by_count":22},{"id":"2305.17040","title":"A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks","created":"2023-05-26","cited_by_count":17},{"id":"1907.04964","title":"A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning","created":"2019-07-11","cited_by_count":12}],"next_cursor":null}